retrodioxide's picture
First Push
e407a72 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 0.8941025733947754,
"min": 0.8941025733947754,
"max": 2.8733537197113037,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 8536.8916015625,
"min": 8536.8916015625,
"max": 29426.015625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 13.02966022491455,
"min": 0.18117116391658783,
"max": 13.02966022491455,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2540.78369140625,
"min": 35.1472053527832,
"max": 2645.37646484375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.07036645465111588,
"min": 0.06295531419483251,
"max": 0.07609749448420189,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.2814658186044635,
"min": 0.25182125677933004,
"max": 0.36641283882964476,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.18403801665294406,
"min": 0.10265381571348281,
"max": 0.27692420254735384,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.7361520666117762,
"min": 0.41061526285393124,
"max": 1.3225447345598074,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.5,
"min": 3.2954545454545454,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1122.0,
"min": 145.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.5,
"min": 3.2954545454545454,
"max": 25.563636363636363,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1122.0,
"min": 145.0,
"max": 1406.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1722171721",
"python_version": "3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.1+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1722172243"
},
"total": 521.3985859400001,
"count": 1,
"self": 0.6473170790001177,
"children": {
"run_training.setup": {
"total": 0.061824357999967106,
"count": 1,
"self": 0.061824357999967106
},
"TrainerController.start_learning": {
"total": 520.689444503,
"count": 1,
"self": 0.7589471519950166,
"children": {
"TrainerController._reset_env": {
"total": 3.461195513000007,
"count": 1,
"self": 3.461195513000007
},
"TrainerController.advance": {
"total": 516.3712629950052,
"count": 18200,
"self": 0.35420182099699105,
"children": {
"env_step": {
"total": 516.0170611740082,
"count": 18200,
"self": 339.6238415020084,
"children": {
"SubprocessEnvManager._take_step": {
"total": 176.0203311420015,
"count": 18200,
"self": 1.7806127639951228,
"children": {
"TorchPolicy.evaluate": {
"total": 174.2397183780064,
"count": 18200,
"self": 174.2397183780064
}
}
},
"workers": {
"total": 0.3728885299982494,
"count": 18200,
"self": 0.0,
"children": {
"worker_root": {
"total": 519.1302003659911,
"count": 18200,
"is_parallel": true,
"self": 257.1130351969797,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.006006042999956662,
"count": 1,
"is_parallel": true,
"self": 0.0037582600000405364,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.002247782999916126,
"count": 10,
"is_parallel": true,
"self": 0.002247782999916126
}
}
},
"UnityEnvironment.step": {
"total": 0.04330181799991806,
"count": 1,
"is_parallel": true,
"self": 0.0011017639999408857,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.00043879899999410554,
"count": 1,
"is_parallel": true,
"self": 0.00043879899999410554
},
"communicator.exchange": {
"total": 0.036544753000043784,
"count": 1,
"is_parallel": true,
"self": 0.036544753000043784
},
"steps_from_proto": {
"total": 0.0052165019999392825,
"count": 1,
"is_parallel": true,
"self": 0.00043292099951486307,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0047835810004244195,
"count": 10,
"is_parallel": true,
"self": 0.0047835810004244195
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 262.0171651690114,
"count": 18199,
"is_parallel": true,
"self": 12.046500328019533,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 6.39888324200308,
"count": 18199,
"is_parallel": true,
"self": 6.39888324200308
},
"communicator.exchange": {
"total": 205.45127224900705,
"count": 18199,
"is_parallel": true,
"self": 205.45127224900705
},
"steps_from_proto": {
"total": 38.12050934998172,
"count": 18199,
"is_parallel": true,
"self": 7.586376055979144,
"children": {
"_process_rank_one_or_two_observation": {
"total": 30.534133294002572,
"count": 181990,
"is_parallel": true,
"self": 30.534133294002572
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.0001276929999676213,
"count": 1,
"self": 0.0001276929999676213,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 510.1609318030156,
"count": 777197,
"is_parallel": true,
"self": 16.638525736934753,
"children": {
"process_trajectory": {
"total": 286.3459804160814,
"count": 777197,
"is_parallel": true,
"self": 285.6432995130815,
"children": {
"RLTrainer._checkpoint": {
"total": 0.7026809029998731,
"count": 4,
"is_parallel": true,
"self": 0.7026809029998731
}
}
},
"_update_policy": {
"total": 207.1764256499995,
"count": 90,
"is_parallel": true,
"self": 61.82409029300209,
"children": {
"TorchPPOOptimizer.update": {
"total": 145.3523353569974,
"count": 4587,
"is_parallel": true,
"self": 145.3523353569974
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09791114999984529,
"count": 1,
"self": 0.0009616180000193708,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09694953199982592,
"count": 1,
"self": 0.09694953199982592
}
}
}
}
}
}
}